Update tembo-ai chart (#819)

Co-authored-by: Steven Miller <sjmiller609@gmail.com>

charts/tembo-ai/Chart.yaml

@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.1.1
+version: 0.1.2
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

charts/tembo-ai/templates/inference-service/statefulset.yaml

@@ -53,6 +53,14 @@ spec:
               path: {{ .Values.inferenceService.readinessProbe.path }}
               port: {{ .Values.inferenceService.readinessProbe.port }}
           {{- end }}
+          {{- if .Values.inferenceService.startupProbe.enabled }}
+          startupProbe:
+            httpGet:
+              path: {{ .Values.inferenceService.startupProbe.path }}
+              port: {{ .Values.inferenceService.startupProbe.port }}
+            failureThreshold: {{ .Values.inferenceService.startupProbe.failureThreshold }}
+            periodSeconds: {{ .Values.inferenceService.startupProbe.periodSeconds }}
+          {{- end }}
           resources:
             {{- toYaml .Values.inferenceService.resources | nindent 12 }}
           {{- with .Values.inferenceService.args }}

charts/tembo-ai/values.yaml

@@ -77,7 +77,7 @@ inferenceGateway:
 
 inferenceService:
   image:
-    repository: vllm/vllm-openai
+    repository: quay.io/tembo/inference
     pullPolicy: IfNotPresent
     tag: latest
   resources:
@@ -97,6 +97,12 @@ inferenceService:
     enabled: true
     path: /health
     port: http
+  startupProbe:
+    enabled: true
+    path: /startup
+    port: http
+    failureThreshold: 30
+    periodSeconds: 10
   replicaCount: 1
   externalSecrets:
     refreshInterval: "5m"